Is tuning a model for this task allowed?
An llm like llama?
https://ai.stackexchange.com/questions/23221/how-is-bert-different-from-the-original-transformer-architecture/23683#23683
An llm like llama?
https://ai.stackexchange.com/questions/23221/how-is-bert-different-from-the-original-transformer-architecture/23683#23683